Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Dragoon0x/canon --skill canon-toastsgit clone --depth 1 https://github.com/Dragoon0x/canonWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dragoon0x/canon/canon-toasts)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-toasts"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-toasts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-toasts"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-toasts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00086 | $0.02059 |
| Opus 5.5 | $0.00034 | $0.00824 |
| Sonnet 5.5 | $0.00017 | $0.00412 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade A, and why
canon-toasts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Toasts
A toast is cheap feedback for safe actions. It is not the answer to every UI question. Before reaching for a toast, ask whether an inline message, banner, or silence would serve better.
When to use a toast
| Use a toast | Don't use a toast |
|---|---|
| Confirm a reversible action with optional Undo | Confirm a destructive action (use modal) |
| Show a background success ("Message sent") | Show a critical error needing action (use inline or modal) |
| Report completion of an async operation | Communicate persistent state (use banner) |
| Flash a brief info message ("Copied to clipboard") | Give instructions ("Now do step 2") |
| Surface a non-blocking error ("Couldn't save draft") | Confirm something users must definitely see |
Rule of thumb: toasts should never interrupt and never be required for the user to see. If users must see it, it's not a toast.
Toast vs banner vs inline vs modal
| Pattern | Persistence | Location | Use |
|---|---|---|---|
| Toast | Auto-dismiss | Edge of viewport | Transient feedback |
| Banner | Stays until action or dismissed | Top of page/section | Persistent system state (you're offline, your subscription expired) |
| Inline | Attached to related element | Within flow | Validation errors, field-level hints |
| Modal | Blocks until resolved | Overlay | Critical decisions |
Wrong pattern picks waste attention. Offline? Banner, not toast. Form field error? Inline, not toast.
Duration
| Toast length | Duration |
|---|---|
| Short (1–4 words) | 3 seconds |
| Default (short sentence) | 4 seconds |
| With action (has Undo/Retry button) | 5–7 seconds |
| Persistent (on user demand) | Until dismissed |
The timer pauses on hover and focus — critical for screen reader + motor-impaired users.
Material snackbar default is 4 seconds without action, 10 seconds with action. Modern practice trends shorter (4–6).
Position
| Position | Use |
|---|---|
| Bottom-center | Mobile, single-column apps |
| Bottom-right | Desktop web, dashboards |
| Top-right | Desktop apps that use bottom for primary content |
| Top-center | Safari mobile back button conflict, avoid |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 230 lines · 86 tokens per session scan A 8000032ba117
canon-toasts is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 86 tokens to every session and 2,059 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
canon-toasts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-toastsDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 86 | Claude Code, Codex |
| accessibilitydiegosouzapw/awesome-omni-skills | Skill | 170 | 4mo ago | MIT | C | 119 | Claude Code, Codex |
| accessibilityericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 86 | Claude Code, Codex |
| accessibility-auditoyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 29 | Claude Code |
| a11y-auditgreglas75/zuvo | Skill | 7 | 3d ago | MIT | A | 147 | Claude Code |
| axe-audittonone-ai/tonone | Skill | 77 | 23d ago | MIT | A | 47 | Claude Code |
| accessibility-compliance-accessibility-audit-v2diegosouzapw/awesome-omni-skills | Skill | 170 | 4mo ago | MIT | A | 76 | Claude Code |